# Evaluating Model Performance with Hard-Swish Activation Function Adjustments

arXiv: https://arxiv.org/abs/2410.06879 · HTML: https://mlsanity.com/paper/2410.06879/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 5 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Builds on (most cited first, 3 of 3)

- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)

## Built on by (most cited first, 3 of 3)

- [Efficient Frame Extraction: A Novel Approach Through Frame Similarity and Surgical Tool Tracking for Video Segmentation](https://mlsanity.com/paper/2501.11153/) (2025)
- [LoKA: Low-precision Kernel Applications for Recommendation Models At Scale](https://mlsanity.com/paper/2605.10886/) (2026)
- [Extended KAFR: A kinematic-adaptive paradigm for the efficient analysis of surgical video](https://mlsanity.com/paper/2608.01058/) (2026)

## Abstract (arXiv)

In the field of pattern recognition, achieving high accuracy is essential. While training a model to recognize different complex images, it is vital to fine-tune the model to achieve the highest accuracy possible. One strategy for fine-tuning a model involves changing its activation function. Most pre-trained models use ReLU as their default activation function, but switching to a different activation function like Hard-Swish could be beneficial. This study evaluates the performance of models using ReLU, Swish and Hard-Swish activation functions across diverse image datasets. Our results show a 2.06% increase in accuracy for models on the CIFAR-10 dataset and a 0.30% increase in accuracy for models on the ATLAS dataset. Modifying the activation functions in architecture of pre-trained models lead to improved overall accuracy.